Prompt Cards

Reproducible Research DAG
Design a DAG (Airflow/Prefect) for reproducible research: crawl→retrieve→synthesize→verify→export. Include artifact hashing and cache invalidation rules.
Tags: reproducibility, pipelines, DAG, caching, hashing
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Structured Findings Exporter
Create an exporter that converts answers into JSON/CSV with fields (claim,evidence,source_url,confidence,timestamp). Provide schemas and sample exports.
Tags: export, JSON, CSV, structure, schemas
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Multimodal Research (PDF/Tables/Images)
Specify table extraction, PDF figure capture, and caption grounding. Define when to quote vs paraphrase, and include a screenshot-to-citation workflow.
Tags: multimodal, PDF, tables, images, grounding
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Live Change-Detection Watchers
Design watchers for tracked topics that diff sources and trigger re-summaries when material changes occur. Provide noise filters and notification policy.
Tags: change-detection, watchers, notifications, diffing, automation
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Synthetic QA Set Generator (With Citations)
Create a pipeline that generates questions from documents, with required answer spans and citations. Provide filters for ambiguity and leakage checks.
Tags: datasets, QA, synthesis, citations, filters
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Attribution-Aware Eval Harness
Build an eval that scores ground-truth attribution (exact passage match), answer faithfulness, and coverage. Provide dataset schema and a nightly regression plan.
Tags: evaluation, attribution, faithfulness, coverage, datasets
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Cost/Latency Router for Tools & Models
Propose a router that routes by budget and SLA: small model for recall, larger for synthesis, tools only when signal warrants. Provide policy examples and guardrails.
Tags: routing, cost, latency, policies, models
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Session Memory & Research Notebook
Create a memory layer that stores hypotheses, decisions, and unresolved questions. Provide schemas, TTL rules, and a notebook export (Markdown/CSV).
Tags: memory, notebook, schema, export, retention
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Human-in-the-Loop UI for Evidence
Design a UI: inline citations, hover previews, source quality badges, and ‘expand to passage’. Include keyboard flows and accessibility specs (WCAG). Output wireframes and event schema.
Tags: UX, UI, citations, accessibility, wireframes
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Domain-Safe Modes (Medical/Legal)
Specify constrained modes with scope limits, consent prompts, guideline links, and mandatory citation density. Provide refusal templates and domain-specific disclaimers.
Tags: governance, medical, legal, safety, mode-switch
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Multilingual Cross-Lingual Research
Create a cross-lingual flow: detect language, translate queries, use multilingual embeddings, and cite in user language while preserving original quotes. Provide locale heuristics and typography rules.
Tags: multilingual, embeddings, translation, citations, locale
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:
Prompt-Injection & Sandbox Guardrails
Draft defenses for tool-using agents: content sanitization, domain allowlists, URL reputation, and read-only sandboxes. Provide red-team prompts and pass/fail gates.
Tags: security, prompt-injection, sandbox, red-team, policies
Author: Assistant
Created at: 2025-12-16 00:00:00
Average Rating:
Total Ratings:

Curio AI Brain

Available in Chrome Web Store!